Upload 2 files

inference.py

@@ -0,0 +1,31 @@
+
+####   text to Image  on Gradio UI 
+import torch
+from diffusers import DiffusionPipeline
+import gradio as gr
+
+
+# Provide the file path to your locally stored model file
+model_file_path = "/model/file/path/to/model/directory/"
+
+# Provide the url to model id
+url = "runwayml/stable-diffusion-v1-5"
+
+# Load the safetensor model 
+pipe = DiffusionPipeline.from_pretrained(url)
+# Metal performance shader(mps) to optimize infernece using Mac built-in gpu :          pipe = pipe.to("mps")
+
+def predict(text):
+    # Ensure pipe(text) returns the correct output format
+    generated_image = pipe(text).images[0]
+    return generated_image
+
+
+
+demo = gr.Interface(
+    fn=predict,
+    inputs='text',
+    outputs='image',
+)
+
+demo.launch(server_name="0.0.0.0", server_port=7000)

main.py

@@ -0,0 +1,30 @@
+
+## mounting Gradio on fast api 
+
+from fastapi import FastAPI
+import gradio as gr 
+from Model.inference import demo
+
+# Define your predict function
+def predict(text):
+    # Your prediction logic here
+    return text[::-1]  # Just an example, reverse the input text
+
+# Create a Gradio interface
+demo = gr.Interface(
+    fn=predict,
+    inputs='text',
+    outputs='text',
+    title='Text Reversal'  # Add a title for the Gradio UI
+)
+
+# Create a FastAPI app
+app = FastAPI()
+
+# Define your root route
+@app.get('/')
+async def root():
+    return 'Gradio is running', 200
+
+# Mount the Gradio interface onto the FastAPI app
+app = gr.mount_gradio_app(app, demo, path='/gradio')